This paper describes a number of log-linear parsing models for an automatically extracted lexicalized grammar. The models are "full" parsing models in the sense that probabilities are defined for complete parses, rather than for independent events derived by decomposing the parse tree. Discriminative training is used to estimate the models, which requires incorrect parses for each sentence in the training data as well as the correct parse. The lexicalized grammar formalism used is Combinatory Categorial Grammar (CCG), and the grammar is automatically extracted from CCGbank, a CCG version of the Penn Treebank. The combination of discriminative training and an automatically extracted grammar leads to a significant memory requirement (over 20 GB), which is satisfied using a parallel implementation of the BFGS optimisation algorithm running on a Beowulf cluster. Dynamic programming over a packed chart, in combination with the parallel implementation, allows us to solve one of the largest-scale estimation problems in the statistical parsing literature in under three hours. A key component of the parsing system, for both training and testing, is a Maximum Entropy supertagger which assigns CCG lexical categories to words in a sentence. The supertagger makes the discriminative training feasible, and also leads to a highly efficient parser. Surprisingly,

This paper describes an extremely lexicalized probabilistic model for fast and accurate HPSG parsing. In this model, the probabilities of parse trees are defined with only the probabilities of selecting lexical entries. The proposed model is very simple, and experiments revealed that the implemented parser runs around four times faster than the previous model and that the proposed model has a high accuracy comparable to that of the previous model for probabilistic HPSG, which is defined over phrase structures. We also developed a hybrid of our probabilistic model and the conventional phrasestructure-based model. The hybrid model is not only significantly faster but also significantly more accurate by two points of precision and recall compared to the previous model. 1

HPSG parsing

Recently, dependency grammar has gained renewed attention as empirical methods in parsing have emphasized the importance of relations between words, which is what dependency grammars model explicitly, but context-free phrase-structure grammars do not. While there has been much work on formalizing dependency grammar and on parsing algorithms for dependency grammars in the past, there is not a complete generative formalization of dependency grammar based on string-rewriting in which the derivation structure is the desired dependency structure. Such a system allows for the definition of a compact parse forest in a straightforward manner. In this paper, we present a simple generative formalism for dependency grammars based on Extended Context-Free Grammar, along with a parser; the formalism captures the intuitions of previous formalizations while deviating minimally from the much-used Context-Free Grammar. 1

Abstract. We present a formalization of lexicalized Recursive Transition Networks which we call Automaton-Based Generative Dependency Grammar (gdg). We show how to extract a gdg from a syntactically annotated corpus, present a chart parser for gdg, and discuss different probabilistic models which are directly implemented in the finite automata and do not affect the parser. 1

In the first REG competition, researchers proposed several general-purpose algorithms for attribute selection for referring expression generation. However, most of this work did not take into account: a) stylistic differences between speakers; or b) trainable surface realization approaches that combine semantic and word order information. In this paper we describe and evaluate several end-to-end referring expression generation algorithms that take into consideration speaker style and use data-driven surface realization techniques. 1

Abstract not found

Bangalore and Joshi (1999) investigate supertagging as “almost parsing”. In this paper we explore this claim further by replacing their Lightweight Dependency Analyzer with a nonlexical probabilistic chart parser. Our approach is still in the spirit of their work in the sense that lexical information is only used during supertagging; the parser and its probabilistic model only see supertags. 1